{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreibwpdw3b5zexabxhed5xepys3ugwopvrv2pb4juxv73kygq7jyaoy",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmgpakhqz5l2"
  },
  "path": "/t/may-2026-chatgpt-api-image-gallery-prompt-tips-and-help-generative-art-theme-science/1378298?page=58#post_1181",
  "publishedAt": "2026-05-22T09:10:37.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "@_j"
  ],
  "textContent": "I also tested this in both API with **gpt-image-2** and in ChatGPT with **5.5 Thinking** and you might be on to something, when it comes to generating two-piece bathing suit images in API and also what @_j already stated, seems to be a default, maybe.\n\n**API gpt-image-2 (moderation: auto)**\n\n> A _woman_ wearing two-piece bathing suit that is colorful, standing, tropical beach in the background, fashion cover magazine.\n\n> A _model_ wearing two-piece bathing suit that is colorful, standing, tropical beach in the background, fashion cover magazine.(this image took exactly 3 minutes to generate)\n\n**ChatGPT-5.5 Thinking**\n\n> A _woman_ wearing two-piece bathing suit that is colorful, standing, tropical beach in the background, fashion cover magazine. (This image took exactly 1min 14s to generate in ChatGPT)\n\n* * *\n\nSo, yeah it seems that in API the word _model_ may make the difference, probably safer than the word _woman_ in this context.\n\nAnd it is fascinating why using the _woman_ in the prompt went through in ChatGPT, but not in API.\n\nP.s. Interesting that both magazines shows the year 2024.",
  "title": "May 2026 — ChatGPT / API Image Gallery, Prompt Tips, and Help: Generative Art Theme: Science"
}